MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jing, Jiang, Minyue, Yang, Sen, Tan, Xiao, Li, Yingying, Ding, Errui, Wang, Hanli, Wang, Jingdong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918056013332480
author Yang, Jing
Jiang, Minyue
Yang, Sen
Tan, Xiao
Li, Yingying
Ding, Errui
Wang, Hanli
Wang, Jingdong
author_facet Yang, Jing
Jiang, Minyue
Yang, Sen
Tan, Xiao
Li, Yingying
Ding, Errui
Wang, Hanli
Wang, Jingdong
contents The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements. Current state-of-the-art methods often adopt solely either point-level or instance-level representation, overlooking the strong intrinsic relationships between points and instances. In this work, we propose a simple yet efficient framework named MGMapNet (Multi-Granularity Map Network) to model map element with a multi-granularity representation, integrating both coarse-grained instance-level and fine-grained point-level queries. Specifically, these two granularities of queries are generated from the multi-scale bird's eye view (BEV) features using a proposed Multi-Granularity Aggregator. In this module, instance-level query aggregates features over the entire scope covered by an instance, and the point-level query aggregates features locally. Furthermore, a Point Instance Interaction module is designed to encourage information exchange between instance-level and point-level queries. Experimental results demonstrate that the proposed MGMapNet achieves state-of-the-art performance, surpassing MapTRv2 by 5.3 mAP on nuScenes and 4.4 mAP on Argoverse2 respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07733
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
Yang, Jing
Jiang, Minyue
Yang, Sen
Tan, Xiao
Li, Yingying
Ding, Errui
Wang, Hanli
Wang, Jingdong
Computer Vision and Pattern Recognition
The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements. Current state-of-the-art methods often adopt solely either point-level or instance-level representation, overlooking the strong intrinsic relationships between points and instances. In this work, we propose a simple yet efficient framework named MGMapNet (Multi-Granularity Map Network) to model map element with a multi-granularity representation, integrating both coarse-grained instance-level and fine-grained point-level queries. Specifically, these two granularities of queries are generated from the multi-scale bird's eye view (BEV) features using a proposed Multi-Granularity Aggregator. In this module, instance-level query aggregates features over the entire scope covered by an instance, and the point-level query aggregates features locally. Furthermore, a Point Instance Interaction module is designed to encourage information exchange between instance-level and point-level queries. Experimental results demonstrate that the proposed MGMapNet achieves state-of-the-art performance, surpassing MapTRv2 by 5.3 mAP on nuScenes and 4.4 mAP on Argoverse2 respectively.
title MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.07733